Sign In

ReMasterXL

293
2.5k
50
Verified:
SafeTensor
Type
Checkpoint Merge
Stats
896
Reviews
Published
Mar 8, 2024
Base Model
SDXL 1.0
Hash
AutoV2
601B186570
default creator card background decoration
cinoai's Avatar
cinoai

ReMaster+1.2.2

ReMaster+ 1.2.2 is a merged model from 1.2.1 and BAXL

thanks to 4BEraser (I actually used the BAXL with minus weight, LOL)

BAXL doesn't permit any commercial uses and ReMaster+1.2.2 follows BAXL's permission.

(ReMater+1.2.1 follows Animagine XL 3.0's)

Recipes are in my blog(Merged model ReMaster+ recipes(리마스터+ 레시피))

PS. I recently used ComfyUI. A1111 makes noise sometimes for the base model of Animagine XL 3.0. So, some sample images are not reproduced in A1111


ReMaster+1.2.1

ReMaster+1.2.1 is a merge model based on ReMaster+1.2 and chenkin-anime-hotbaby.

chenkin-anime-hotbaby is a finetuned model of Animagine XL 3.0. Thanks to Chenkin.

Please note that 1.2.1 may generate NSFW images without any NSFW prompts. 1.2 may be suitable for SFW images.

  • nsfw into negative prompts may help this problem but it might not be helpful. So, I recommend adding rating: general into positive prompts and nude, nsfw, sex into negative prompts.

  • Also, best quality and masterpiece can generate NSFW things even though there's no NSFW hint

ReMaster+

I merged ReMaster1.0 with animagine-xl-3.0(Animagine XL V3 - V3.0 | Stable Diffusion Checkpoint | Civitai) (This is really good model to generate anime images. I think this is SOTA model for free)

Thanks to cagliostrolab (Cagliostro Research Lab) (huggingface.co)

Prompting tips:

  • (realistic:0.01) (realistic:0.5) would generate good semi-realistic images. Please check the prompts of the sample images. (realistic:0.01 may cause artifacts)

  • realistic in negative prompts will generate less realistic images.

  • low CFG(less than 7) scale for realistic, high CFG(higher than 7) for animes

Recipes: Merged model ReMaster+ recipes(리마스터+ 레시피) (stablediffusionmaster.blogspot.com)

Please note that the Licence in Animagine XL V3 - V3.0 | Stable Diffusion Checkpoint | Civitai

This model follows the same license of AnimagineXL3


V1.0

I tuned Reproduction(Reproduction | SDXL - 2v1.2 | Stable Diffusion Checkpoint | Civitai) by merging custom LoRas.

Thanks to Aikimi

"gothic, realistic, makeup, masterpiece, best quality" would make good images.

Please see the prompts for sample images.